© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1916
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     încep
    0.78
     centuries
    0.75
    rif
    0.71
     comunic
    0.71
     mécanisme
    0.70
    蒟
    0.70
     biotech
    0.69
    ciaux
    0.66
    喻
    0.66
     modèle
    0.65
    POSITIVE LOGITS
     буквы
    0.77
    sle
    0.74
     sveik
    0.72
    kah
    0.71
     photospheres
    0.69
    shoes
    0.68
     ڪ
    0.68
    見た
    0.67
    ückt
    0.66
    此之外
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.